• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.21-29
• /
• 2023

In this paper, we propose an AI-based system for automatically classifying industry and occupation codes in the population census. The accurate classification of industry and occupation codes is crucial for informing policy decisions, allocating resources, and conducting research. However, this task has traditionally been performed by human coders, which is time-consuming, resource-intensive, and prone to errors. Our system represents a significant improvement over the existing rule-based system used by the statistics agency, which relies on user-entered data for code classification. In this paper, we trained and evaluated several models, and developed an ensemble model that achieved an 86.76% match accuracy in industry and 81.84% in occupation, outperforming the best individual model. Additionally, we propose process improvement work based on the classification probability results of the model. Our proposed method utilizes an ensemble model that combines transfer learning techniques with pre-trained models. In this paper, we demonstrate the potential for AI-based systems to improve the accuracy and efficiency of population census data classification. By automating this process with AI, we can achieve more accurate and consistent results while reducing the workload on agency staff.

• Korea Journal of Hospital Management
• /
• v.18 no.2
• /
• pp.15-32
• /
• 2013

Few public health researchers have paid research attention to the location of medical institutions in Korea. Previous studies were published in geography journals, and relied on limited data in terms of geographic regions and the type of medical institutions. This study utilized nationwide data covering 8 types of medical institutions. We obtained data from Health Insurance Review and Assessment Service and National Population and Housing Census. The correlation coefficients of resident, daytime, university-graduate population, and the population of different age groups (fewer than 15, 15~64, 65 or more) were compared to understand their relative association with the location of medical institutions. Medical clinic, dental clinic, oriental medical clinic, and pharmacy, all of which are almost completely operated by private sector, showed strong positive correlation with population. Hospital-level medical institutions, which are operated by both public and private sector, had moderate positive correlation. Daytime population and university-graduate population, rather than resident population, were more correlated with the location of medical clinics. The correlation coefficients of the population of 15~64 age group and the location of medical institutions were greater than that of other age groups. The results showed that daytime and university-graduate population are more important than resident population to explain the location of medicalrelated facilities. The results also suggests that the population of age groups (especially, 15~64) might be one of important influence factors in the location of medical institutions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.11
• /
• pp.5508-5513
• /
• 2013

This paper seeks to empirically analyze the effect of WLFP on fertility in Korea using the 1985~2010 Korean Population and Housing Census 1% Sample data. The results show that except in year 1985(+0.336) WLFP had a significant negative effect on fertility rates in years 1990, 2000, 2005, 2010. The size of the negative effect increases from 1990(-0.611) to 2005(-2.273). In 2010(-0.793), however, the negative effect considerably decreases when compared with the 2005 result. This alleviation is partially due to policies that have promoted compatibility between work and family life. Policy makers should therefore focus on expansion of policies for the compatibility of work and family, and give more attention to increasing take-up rate for the current policies.

• Journal of the Korean Geographical Society
• /
• v.30 no.3
• /
• pp.311-323
• /
• 1995

This study attempts to examine the location and district of elementary schools at Chongro-gu. For the convenience of the analysis, the data are analysed with the methods of GIS network model. For the purpose data was collected from Statistical Yearbook of Education in 1994 and Census of Housing and Population in 1990. Results may be summarized as follows. First of all, spatial pattern of elementary school at Chongro-gu shows outward diffusion because of problems, rising of land value, and out-migration of population in the area. Secondly, for the analysis of locational situation this paper uses the data such as population of 5-9 age, the number of housing, accessibility, and land value. The location of elementary school is ciassified into 4 types; the best area, better area, worse area, the worst area. The best area is Pyongchana-dong, Buam-dong, and Ewha-dong and the worst area is Chongro 1ga-dona, Chonaro 2ga-dong and Sechongno-dong. Thirdly, the alternative plans of school district are presented for the maximum equity and efficience, and security of school attendantes. The former emphasizes the minimization of commuting distance, the later emphasizes the minimization of the an comfortable facilities such as main streets in school district. Present school district which is based upon administrative dong should be changed to roadbased school district.

• Korea journal of population studies
• /
• v.16 no.2
• /
• pp.125-139
• /
• 1993

Korea has successfully achieved a lowered fertility level owing to the strong population control policy and effective family planning program. Along with fertility decline and decreased number of children in family, average number of household members has decreased and nontraditional households such as one person household and households composed of unrelated individuals have prolifirated, even though the absolute number of them are found minimal in Korea. However in recent years several data and survey results suggest that one person households are gradually in the increasing trend. The study aimed at investigating the real state of one person households in Korea and next analyzing the proportional distribution of one person households by a few socioeconomic characteristics, thus providing basic for eatablishing far-singhted population and social welfare policy in the future. Korea has experienced high growth rate of economy through government-led development plans starting from the 1960s. During the past three decades, Korea has shifted from the agricultural state to the industrialized one. In compliance with the economic growth, urbanization and industrialization have brought about rural-to-urban migration and a great bulk of young population migrated to urban areas, who are seeking for educational and job opportunities. Korean society has also been under drastic change in every aspect of life involving norms, tradition, and attitude, etc. Therefore, in spite of the prejudice on 'living alone' still remaining, young people gradually leave parents and home, and further form nontraditional households in urban areas. Current increase in the number of one person households is partly attributable to the increase in high female educational attainment and female participation in economic activities. As the industrial structure in Korea changes from primary into secondary and tertiary industries, job opportunities for service/sales and manufacturing are opened to young female labor force in the process of industrialization. Contrary to the formation of one person households by young people, the aged single households are composed when children in family leave one by one because of marriage, education, employment. In particular, a higher proportion of aged female single households occur in rural areas due to the mortality difference by sex. Based on the data released form the 1990 Population and Housing Census and National Fertility and Family Health Survey in 1985 and 1991, the study tried to examine the state of one person households in Korea. According to Census data, the number of one person households increased to 1, 021, 000 in 1990, comprising 9.0 percent of total households. And the survey reveal that among total 11, 540 households, 8.0 percent, 923 households, are composed of one person households. Generally, the proportion of female single households is greater than that of male ones, and a big proportion of one person households is concentrated in the 25-34 age bracket in urban areas and 65 years and more in rural areas. It is shown than one person householders in urban areas have higher educational attainment with 59.2 percent high schooling and over in 1991, Job seeking proved to be the main reason for leaving home and forming one person households. The number of young female single households with higher education and economic self-reliance are found nil and the study did not allow to analyze the causal realtionship between female education and employment and one person household formation. However more research and deep analysis on the causal facors on one person household formation using statistical method are believed to be necessary.

• Korea journal of population studies
• /
• v.9 no.2
• /
• pp.67-78
• /
• 1986

With Economic Development Plan, the Korean National Family Plan Program was introduced in early 1960's. The program, which has been a way for constraining population increase, has obtained excellent results. In other word, it has had an important role in controlling the increase in population. The purpose of this study is to analyze the change of fertility rates since 1970 and the lever of completed fertility of Korean women since 1960. There are Age-specific Fertility Rate(ASFR), Total Fertility Rate(TFR), Gross Reproduction Rate(GRR) and Net Reproduction Rate(NRR) etc. in indices of period fertility. It is also possible to be seen the completed fertility rates by using Parity Progression Ratio. The data necessary for this study were obtained from Population & Housing Census Report from the year of 1960 to 1980 and Vital Statistics from 1980 to 1984, which conducted by Economic Planning Board, Republic of Korea. The summarized results of this study were as follows : 1. Age-specific Fertility Fertility Rate(ASFR) has been continuously decreasing till now. The ASFR for the women aged 25 to 29 was higher than those of any other groups and the ASFR for the women aged 20 to 24 was higher than that of the women aged 30 to 34 since the mid 1970's. 2. There are Total Fertility Rate(TFR), Gross Reproduction Rate(GRR) and Ney Reproduction Rate(NRR) etc. in reproduction rates. First of all, TFR and GRR have been declining except late of 1970's and TFR showed 2.23 per ever-married women, GRR was 1.05 in 1982. Next, the change of NRR could not be found without life table by year and only NRR for the time of census was to be found. In 1980, NRR showed 1.27 per ever-married women and the level was still out of reach at replacement level of population. 3. Specific Fertility Rate by Birth Order(SFRBO) showed to be declined continually since 1972. Especially the SFRBO of the third live birth was decreased from about 22 per 1,000 ever-married women in 1972 to 12 or so in 1982. 4. To know the level of completed fertility, the mean number of completed live births per ever-married women was calculated from 1960 to 1980. The number of completed live births was more than 5 per ever-married women by the year of 1975 but have been declining and resulted in 4.69 in 1980.

• The Korean Journal of Applied Statistics
• /
• v.18 no.1
• /
• pp.27-41
• /
• 2005

We made a new sample design for intestinal parasitic infection survey in 2004. We used the 10% sample survey data of 2000 population and housing census as a survey population. Since the infection rates of intestinal parasitics are very low, we applied the relative risk and odds ratio instead of ordinary method such as t-test to study the characteristics from the 1997 survey data. In order to allocate samples to stratum, we used the compromise of Neyman allocation which is the average of three Neyman allocations. And also, we derive estimators and variance estimators of the estimators.

• Korea journal of population studies
• /
• v.18 no.2
• /
• pp.98-114
• /
• 1995

Since 1962 the Korean society has undergone a rapid transformation under government policies to achieve maximum economic growth. Urbanization via massive rural to urban migration has been observed to be connected with a rapid economic development. Based on the data from the government publications such as Population and Housing Census Reports and Korean Urban Yearbooks, this study measures inequalities in terms of the distribution of urban population. In a historical context, the pace of urbanization during the period 1966-1970 was characterized as the most rapid and the urban-rural growth difference(URGD), which is a valuable measure of the pace of urbanization, was the highest. In terms of regional pattern, Seoul dominated the urbanization picture of Korea during the period 1966-1970. Its annual growth rate was the fastest among those shown during the period 1960 to 1990 and also highest. However, Seoul's primacy was pulled down since 1970. The Gini coefficient, which is the most common general measure of inequalities in distribution, was the highest in 1980. Since 1980 it has continued to fall. As a result, it was lower in 1990 than in 1970. Despite lowering Gini coefficient, inequalities are still large. A concentration index also showed the same trends as those of Gini coefficent.

• Journal of the Korean Geographical Society
• /
• v.48 no.4
• /
• pp.509-532
• /
• 2013

Minimum Housing Standard is an instrument to cope with the problems of public health and community hygiene, deterioration of working class housing conditions appeared commonly in the process of capitalist industrialization and rapid rural-to-urban migration. This paper aims to examine the institutionalization of histories of minimum housing standard in the advanced countries, and analyze the spatio-temporal changes and characteristics of households failing to meet the New Minimum Housing Standard in Seoul Metropolitan since 1995. The analysis of this paper is based on the census data on population and housing. The results are as follows; Households failing to meet the New Minimum Housing Standard in Seoul are 501,000 households(1.368 million person, 14.4%). This means Seoul has overtaken the national average 11.8% for the first time and there are structurally marginal band of households who can not improve the housing conditions by themselves. In addition, the fact that the rate of Seoul households living in the marginal shelter including the basement and rooftop room is the highest in Korea means the housing quality issues of Seoul is serious. Spatial distribution of households failing to meet the standard is divided into the northeast area and the southwest area in Seoul. Main features of the households are female-headed families, middle and old-aged people, divorce families, lower educated people, under and graduate students, non-apartments, dweller in 15~20 year old houses.

• Journal of the Korea Convergence Society
• /
• v.12 no.4
• /
• pp.23-30
• /
• 2021

An Automated Industry and Occupation Coding System assigns statistical classification code to the enormous amount of natural language data collected from people who write about their industry and occupation. Unlike previous studies that applied information retrieval, we propose a system that does not need an index database and gives proper code regardless of the level of classification. Also, we show our model, which utilized KoBERT that achieves high performance in natural language downstream tasks with deep learning, outperforms baseline. Our method achieves 95.65%, 91.51%, and 97.66% in Occupation/Industry Code Classification of Population and Housing Census, and Industry Code Classification of Census on Basic Characteristics of Establishments. Moreover, we also demonstrate future improvements through error analysis in the respect of data and modeling.